Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

gemini-2.0-flash-thinking-exp-1219 模型的回复异常 #5475

Closed
dupl opened this issue Jan 16, 2025 · 6 comments · Fixed by #5477
Closed

gemini-2.0-flash-thinking-exp-1219 模型的回复异常 #5475

dupl opened this issue Jan 16, 2025 · 6 comments · Fixed by #5477
Labels
🐛 Bug Something isn't working | 缺陷 Gemini released

Comments

@dupl
Copy link
Contributor

dupl commented Jan 16, 2025

📦 Environment

Vercel, Netlify

📌 Version

1.45.11

💻 Operating System

Windows, Ubuntu

🌐 Browser

Chrome, Edge

🐛 Bug Description

1.45.11版本之后,即4d1a4cd800e05c488fbe4942bbfe8ef75eb5a914这个提交之后,vercel和netlify部署的 gemini-2.0-flash-thinking-exp-1219 模型,不能正常使用了。比如问一下“天空为什么是蓝色的”,回复只有一个单词,如“Thing”、“We”、“Let”,或者回复空白,部署该提交之前的版本则正常回复。

📷 Recurrence Steps

No response

🚦 Expected Behavior

No response

📝 Additional Information

No response

@dupl dupl added the 🐛 Bug Something isn't working | 缺陷 label Jan 16, 2025
@github-project-automation github-project-automation bot moved this to Roadmap - Chat 1.x in Lobe Chat Routine Jan 16, 2025
@lobehubbot
Copy link
Member

👀 @dupl

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事,并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

@dosubot dosubot bot added the Gemini label Jan 16, 2025
Copy link

dosubot bot commented Jan 16, 2025

Hey @dupl! 👋 I'm here to help you with bug fixes, answer questions, and even guide you to become a contributor. Let's tackle this together!

The issue you're experiencing with the gemini-2.0-flash-thinking-exp-1219 model after the commit 4d1a4cd800e05c488fbe4942bbfe8ef75eb5a914 might be related to changes in the configuration or code that affect response generation. However, I couldn't find specific details about changes in that commit that could cause this behavior.

The configuration file src/config/aiModels/google.ts contains settings specific to this model, such as abilities, context window tokens, and max output, but there is no indication that these settings were altered in the recent update [1].

To troubleshoot, you might want to:

  1. Check if there were any changes in the codebase related to response generation logic or model integration that coincide with the problematic commit.
  2. Review any recent updates or patches that might address this issue.
  3. Consider rolling back to a previous version before the commit to verify if the issue persists.

If the problem continues, further investigation into the specific changes made in the commit might be necessary.

To continue talking to Dosu, mention @dosu.


Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other

@arvinxx
Copy link
Contributor

arvinxx commented Jan 16, 2025

@sxjeru 来看下~

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿


@sxjeru Let’s take a look~

@github-project-automation github-project-automation bot moved this from Roadmap - Chat 1.x to Done in Lobe Chat Routine Jan 16, 2025
@lobehubbot
Copy link
Member

@dupl

This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题,可以留言并回复。

@lobehubbot
Copy link
Member

🎉 This issue has been resolved in version 1.46.6 🎉

The release is available on:

Your semantic-release bot 📦🚀

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🐛 Bug Something isn't working | 缺陷 Gemini released
Projects
Status: Done
Development

Successfully merging a pull request may close this issue.

3 participants